Performance of Large Language Models in a National Medical Licensing Examination: A Two-Year Comparative Study of Gemini 3 Pro, DeepSeek V3.1, and GPT-5.2 in Traditional Chinese Medicine

Abstract

<title>Abstract</title> Background Large language models (LLMs) are increasingly integrated into medical education and assessment. However, their performance in high-stakes, non-English medical licensing examinations—particularly within culturally distinct medical systems such as Traditional Chinese Medicine (TCM)—remains insufficiently evaluated. Objective This study aimed to systematically compare the performance of Gemini 3 Pro, DeepSeek V3.1, and GPT-5.2 in the Chinese National Traditional Chinese Medicine Licensing Examination (TCMLE) over two consecutive years (2023 and 2024), and to assess their potential implications for TCM education. Methods All original examination questions from the 2023 and 2024 TCMLE (600 questions per year), encompassing all official question types and examination units, were independently input into each model in Chinese. Model responses were evaluated based on accuracy. Comparative analyses across models, question types, and examination units were conducted using chi-square tests, with statistical significance set at P&lt;.05. Results DeepSeek V3.1 demonstrated significantly higher overall accuracy than Gemini 3 Pro and GPT-5.2 in both 2023 (87.1%) and 2024 (86.7%) (P&lt;.001 for all comparisons). Gemini 3 Pro exhibited moderate and relatively stable performance across both years, whereas GPT-5.2 achieved the lowest overall accuracy despite a modest improvement from 2023 to 2024. Notably, DeepSeek V3.1 showed particular strength in structured and clinically oriented question formats and in foundational knowledge units. Conclusions Linguistic and cultural alignment plays a critical role in LLM performance on specialized medical licensing examinations. Locally optimized models such as DeepSeek V3.1 may serve as valuable auxiliary tools in TCM education, particularly for examination preparation and knowledge reinforcement, although careful human oversight remains essential.

Ähnliche Arbeiten